def fromMap(self, map_query2target, use_strand=None):
"""return a map between query to target."""
self.mNMatches = map_query2target.getNumAligned()
f = alignlib_lite.py_AlignmentFormatBlat(map_query2target)
self.mQueryFrom, self.mQueryTo, self.mSbjctFrom, self.mSbjctTo, \
self.mQueryBlockStarts, self.mSbjctBlockStarts, self.mBlockSizes = str(
f).split("\t")
if self.mBlockSizes:
self.mBlockSizes = map(int, self.mBlockSizes[:-1].split(","))
self.mQueryBlockStarts = map(
int, self.mQueryBlockStarts[:-1].split(","))
self.mSbjctBlockStarts = map(
int, self.mSbjctBlockStarts[:-1].split(","))
else:
self.mBlockSizes = []
self.mQueryBlockStarts = []
self.mSbjctBlockStarts = []
self.mNBlocks = len(self.mBlockSizes)
self.mQueryFrom, self.mQueryTo, self.mSbjctFrom, self.mSbjctTo = \
map(int,
(self.mQueryFrom, self.mQueryTo, self.mSbjctFrom, self.mSbjctTo))
# queryfrom and queryto are always forward strand coordinates
if use_strand and self.strand == "-":
self.mQueryFrom, self.mQueryTo = self.mQueryLength - \
self.mQueryTo, self.mQueryLength - self.mQueryFrom
def fromMap(self, map_query2target, use_strand=None):
"""return a map between query to target."""
self.mNMatches = map_query2target.getNumAligned()
f = str(alignlib_lite.py_AlignmentFormatBlat(map_query2target))
self.mQueryFrom, self.mQueryTo, self.mSbjctFrom, self.mSbjctTo, \
self.mQueryBlockStarts, self.mSbjctBlockStarts, self.mBlockSizes = f.split(
"\t")
if self.mBlockSizes:
self.mBlockSizes = list(map(int, self.mBlockSizes[:-1].split(",")))
self.mQueryBlockStarts = list(
map(int, self.mQueryBlockStarts[:-1].split(",")))
self.mSbjctBlockStarts = list(
map(int, self.mSbjctBlockStarts[:-1].split(",")))
else:
self.mBlockSizes = []
self.mQueryBlockStarts = []
self.mSbjctBlockStarts = []
self.mNBlocks = len(self.mBlockSizes)
self.mQueryFrom, self.mQueryTo, self.mSbjctFrom, self.mSbjctTo = \
list(map(int,
(self.mQueryFrom, self.mQueryTo,
self.mSbjctFrom, self.mSbjctTo)))
# queryfrom and queryto are always forward strand coordinates
if use_strand and self.strand == "-":
self.mQueryFrom, self.mQueryTo = self.mQueryLength - \
self.mQueryTo, self.mQueryLength - self.mQueryFrom
def getMapTarget2Query(self):
"""return a map between target to query.
If the strand is "-", the coordinates for query are on
the negative strand.
"""
map_target2query = alignlib_lite.py_makeAlignmentBlocks()
f = alignlib_lite.py_AlignmentFormatBlat(
"%i\t%i\t%i\t%i\t%s\t%s\t%s\n" %
(min(self.mSbjctBlockStarts), max(self.mSbjctBlockStarts),
min(self.mQueryBlockStarts), max(self.mQueryBlockStarts),
",".join([str(x) for x in self.mSbjctBlockStarts]) + ",",
",".join([str(x) for x in self.mQueryBlockStarts]) + ",",
",".join([str(x) for x in self.mBlockSizes]) + ","))
f.copy(map_target2query)
return map_target2query
def getMapTarget2Query(self):
"""return a map between target to query.
If the strand is "-", the coordinates for query are on
the negative strand.
"""
map_target2query = alignlib_lite.py_makeAlignmentBlocks()
f = alignlib_lite.py_AlignmentFormatBlat("%i\t%i\t%i\t%i\t%s\t%s\t%s\n" % (
min(self.mSbjctBlockStarts),
max(self.mSbjctBlockStarts),
min(self.mQueryBlockStarts),
max(self.mQueryBlockStarts),
",".join([str(x) for x in self.mSbjctBlockStarts]) + ",",
",".join([str(x) for x in self.mQueryBlockStarts]) + ",",
",".join([str(x) for x in self.mBlockSizes]) + ","))
f.copy(map_target2query)
return map_target2query
import alignlib_lite as alignlib x = alignlib.py_makeAlignmentBlocks() x.addDiagonal( 10, 100, 0 ) print x.getNumAligned(), x.getRowFrom(), x.getRowTo() f = alignlib.py_AlignmentFormatBlat( x ) print str(f) f.copy( x ) print str(f)
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version="%prog version: $Id: psl2wiggle_stats.py 2781 2009-09-10 11:33:14Z andreas $", usage=globals()["__doc__"])
parser.add_option("-g", "--genome-file", dest="genome_file", type="string",
help="filename with genome.")
parser.add_option("--wiggle-files", dest="wiggle_files", type="string",
help="glob expression for wiggle files [%default].")
parser.add_option("--prefix", dest="prefix", type="string",
help="prefix to add to contig names before lookup [%default].")
parser.add_option("-z", "--from-zipped", dest="from_zipped", action="store_true",
help="input is zipped.")
parser.add_option("--test", dest="test", type="int",
help="test - stop after # rows of parsing [%default].")
parser.add_option("--with-values", dest="with_values", action="store_true",
help="output values in last column [%default].")
parser.set_defaults(wiggle_files="*.data.bz2",
from_zipped=False,
prefix="",
with_values=False,
test=None)
(options, args) = E.Start(parser, add_pipe_options=True)
# open indexed access to wiggles
wiggle_files = glob.glob(options.wiggle_files)
if not wiggle_files:
raise IOError("could not find wiggle files with '%s'" %
options.wiggle_files)
index = Wiggle.WiggleMultiIndexedAccess(wiggle_files,
keep_open=True,
use_cache=False)
iterator = Blat.BlatIterator(sys.stdin)
ninput, noutput, nskipped = 0, 0, 0
options.stdout.write(
"query\tnali\t%s" % ("\t".join(Stats.DistributionalParameters().getHeaders())))
if options.with_values:
options.stdout.write("\tvalues")
options.stdout.write("\n")
while 1:
if options.test and ninput >= options.test:
break
match = iterator.next()
if match is None:
break
ninput += 1
if options.loglevel >= 2:
options.stdlog.write(str(match) + "\n")
# psl always matches on the forward strand
map_genome2query = alignlib_lite.py_makeAlignmentBlocks()
f = alignlib_lite.py_AlignmentFormatBlat("%i\t%i\t%i\t%i\t%s\t%s\t%s\n" % (
match.mSbjctFrom,
match.mSbjctTo,
match.mQueryFrom,
match.mQueryTo,
match.mSbjctBlockStarts,
match.mQueryBlockStarts,
match.mBlockSizes))
f.copy(map_genome2query)
data = index.get(options.prefix + match.mSbjctId,
match.mSbjctFrom,
match.mSbjctTo)
values = []
for x, vv in data:
for v in vv:
if map_genome2query.mapRowToCol(x) >= 0:
values.append(v)
x += 1
if len(values) == 0:
nskipped += 1
continue
noutput += 1
if options.loglevel >= 2:
options.stdlog.write(
"# %s\n" % ",".join(["%5.3f" % v for v in values]))
s = Stats.DistributionalParameters(values)
options.stdout.write("%s\t%i\t%s" % (match.mQueryId,
match.mNMismatches +
match.mNMatches,
str(s)))
if options.with_values:
options.stdout.write(
"\t%s" % ",".join(["%5.3f" % v for v in values]))
options.stdout.write("\n")
if options.loglevel >= 1:
options.stdlog.write(
"# ninput=%i, noutput=%i, nskipped=%i\n" % (ninput, noutput, nskipped))
E.Stop()